In this paper we address the challenging problem of domain adaptation in LiDAR semantic segmentation. We consider the setting where we have a fully-labeled data set from source domain and a target domain with a few labeled and many unlabeled examples. We propose a domain adaptation framework that mitigates the issue of domain shift and produces appealing performance on the target domain. To this end, we develop a GAN-based image-to-image translation engine that has generators with alternating connections, and couple it with a LiDAR semantic segmentation network. Our framework is hybrid in nature in the sense that our model learning is composed of self-supervision, semi-supervision and unsupervised learning. Extensive experiments on benchmark LiDAR semantic segmentation data sets demonstrate that our method achieves superior performance in comparison to state-of-the-art baselines and prior arts.
Domain Adaptation in LiDAR Semantic Segmentation via Hybrid Learning with Alternating Skip Connections
2023-06-04
1499994 byte
Conference paper
Electronic Resource
English
Deep-Skip Net: Research on UAVs Image Semantic Segmentation Technology
Springer Verlag | 2022
|Deep-Skip Net: Research on UAVs Image Semantic Segmentation Technology
British Library Conference Proceedings | 2022
|TransRVNet: LiDAR Semantic Segmentation With Transformer
IEEE | 2023
|